© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 12246
    Prev
    Next
    INDEX
    Explanations

    photo and location descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rasulullah
    -1.02
     нужно
    -1.02
     interessante
    -0.92
     Russel
    -0.91
     curiosa
    -0.91
     theater
    -0.91
    たとえば
    -0.90
     colorful
    -0.88
    襷
    -0.88
     stylized
    -0.87
    POSITIVE LOGITS
     €
    1.30
     whilst
    1.03
    ʽ
    1.01
     Melon
    1.00
    meler
    1.00
    Melon
    0.98
    €
    0.97
     cocktails
    0.96
     villa
    0.94
     independencia
    0.93
    Activations Density 0.019%

    No Known Activations